© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3385
    Prev
    Next
    INDEX
    Explanations

    card, donor, landlord, caregiver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    bell
    -0.10
    cle
    -0.10
    rod
    -0.10
     fils
    -0.10
    rant
    -0.10
    eil
    -0.09
    nds
    -0.09
    ilda
    -0.09
     inher
    -0.09
    nen
    -0.09
    POSITIVE LOGITS
    ism
    0.13
    hip
    0.10
    &E
    0.09
    /client
    0.09
    /ref
    0.09
     OR
    0.09
    /fast
    0.09
    -funded
    0.08
    ess
    0.08
    inee
    0.08
    Activations Density 0.003%

    No Known Activations